Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2821 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.7807. Min Act: -0.0002

Data Index: 689850 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.5529. Min Act: -0.0002

Data Index: 753996 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.6952. Min Act: -0.0002

Data Index: 315617 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.7154. Min Act: -0.0002

Data Index: 965042 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.6488. Min Act: -0.0002

Data Index: 529196 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.5794. Min Act: -0.0002

Data Index: 492972 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.6148. Min Act: -0.0002

Data Index: 378497 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.6546. Min Act: -0.0002

Data Index: 754464 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.6100. Min Act: -0.0002

Data Index: 673880 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.6293. Min Act: -0.0002

Data Index: 76954 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.6195. Min Act: -0.0003

Data Index: 370660 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.6776. Min Act: -0.0002

Data Index: 1277654 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.6600. Min Act: -0.0003

Data Index: 496430 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.6376. Min Act: -0.0002

Data Index: 47105 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.6371. Min Act: -0.0002

Data Index: 457455 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.6331. Min Act: -0.0002

Data Index: 1212363 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.6077. Min Act: -0.0003

Data Index: 507114 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.6255. Min Act: -0.0002

Data Index: 458030 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.5484. Min Act: -0.0002

Data Index: 276084 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 0.7807. Min Range: -0.7807

Max Act: 0.5242. Min Act: -0.0003

Data Index: 183613 (C4 (Web Text))

Max Activating Token Index: 132